Development of an Airflow-Based Automated Pipeline for Constructing Common Data Model Integrating Structured and Unstructured Medical Data
Studies in Health Technology and Informatics · 21.05.2026
DOI: 10.3233/shti260431 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Sunah Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Electronic Health Records. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The growing use of multimodal clinical data requires standardized and automated construction of Common Data Models (CDMs). This study presents an Apache Airflow–based automated pipeline for OMOP CDM v5.4 that integrates structured EMR data and unstructured sources. Applied to Seoul National University Hospital data (2004–2024), the pipeline generated 47 CDM tables from approximately 3.7 million patients and incorporated nearly 10 million unstructured data instances. The proposed workflow improves reproducibility and scalability of CDM construction and supports future multi-institutional deployment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
- Department of Clinical Medical Science, Seoul National University College of Medicine, Republic of Korea.
- Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Republic of Korea.
- Department of Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
- Department of Urology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
- Office of Hospital Information, Seoul National University Hospital, Seoul, Republic of Korea.
Zitieren
APA
Yang, S., Kim, K., & Jeong, C. W. (2026). Development of an Airflow-Based Automated Pipeline for Constructing Common Data Model Integrating Structured and Unstructured Medical Data. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260431
Vancouver
Yang S, Kim K, Jeong CW. Development of an Airflow-Based Automated Pipeline for Constructing Common Data Model Integrating Structured and Unstructured Medical Data. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260431
BibTeX
@article{Yang2026,
author = {Yang, Sunah and Kim, Kwangsoo and Jeong, Chang Wook},
title = {Development of an Airflow-Based Automated Pipeline for Constructing Common Data Model Integrating Structured and Unstructured Medical Data},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260431}
}
EUVIMED